Access Google's powerful 27 billion parameter language model through a simple REST API.
Multi-turn chat completions for conversations and interactive AI applications. with 128K token context window, you can send entire books, long documents, or extensive conversation histories in a single request.
Simple Conversation
{
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
],
"temperature": 0.7,
"max_tokens": 100
}Multi-turn Conversation
{
"messages": [
{
"role": "system",
"content": "You are a helpful travel assistant."
},
{
"role": "user",
"content": "What's the best time to visit Japan?"
},
{
"role": "assistant",
"content": "Spring (March to May) and autumn (September to November) are the best times to visit Japan for mild weather and beautiful cherry blossoms or fall colors."
},
{
"role": "user",
"content": "What about the food there?"
}
],
"temperature": 0.8,
"max_tokens": 150
}Programming Help
{
"messages": [
{
"role": "system",
"content": "You are an expert JavaScript programmer."
},
{
"role": "user",
"content": "How do I reverse a string in JavaScript?"
}
],
"temperature": 0.5,
"max_tokens": 200
}Chat Completions - Endpoint Features
| Object | Description |
|---|---|
Request Body |
[Required] Json |
{"id":"chatcmpl-1775011951099","object":"chat.completion","created":1775011951,"model":"gemma-3-27b-it","choices":[{"index":0,"message":{"role":"assistant","content":"The capital of France is **Paris**. \n\nIt's known for iconic landmarks like the Eiffel Tower, the Louvre Museum, and the Arc de Triomphe, as well as its fashion, cuisine, and culture.\n\n\n\n"},"finish_reason":"stop"}],"usage":{"prompt_tokens":15,"completion_tokens":47,"total_tokens":62}}
curl --location --request POST 'https://zylalabs.com/api/12286/gemma+3+api/23070/chat+completions' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
],
"temperature": 0.7,
"max_tokens": 100
}'
| Header | Description |
|---|---|
Authorization
|
[Required] Should be Bearer access_key. See "Your API Access Key" above when you are subscribed. |
No long-term commitment. Upgrade, downgrade, or cancel anytime. Free Trial includes up to 50 requests.
The Chat Completions endpoint returns a JSON object containing the assistant's response to user queries. This includes the assistant's message, the role of the message (user or assistant), and metadata such as the completion ID and token usage.
Key fields in the response include "id" (unique identifier), "object" (type of response), "created" (timestamp), "model" (model used), "choices" (array of responses), and "usage" (token counts for prompt, completion, and total).
The response data is structured as a JSON object. It contains an array of "choices," where each choice includes the assistant's message and its role. The "usage" field provides details on token consumption, helping users understand their request's complexity.
Users can customize requests with parameters such as "temperature" (controls randomness), "max_tokens" (limits response length), and "top_p" (nucleus sampling). These parameters allow for tailored responses based on user needs.
The endpoint provides information on a wide range of topics, including general knowledge, coding assistance, creative writing, and more. It supports multi-turn conversations, allowing for context-aware interactions.
Users can extract the assistant's message from the "choices" array to display responses in applications. The "usage" field helps monitor token consumption, which is useful for optimizing requests and managing data flow.
Typical use cases include building AI chatbots for customer support, generating content for blogs, providing coding assistance, and creating educational tools. The API's versatility supports various applications across industries.
Data accuracy is maintained through continuous training of the underlying language model on diverse datasets. Regular updates and quality checks ensure that the model provides relevant and accurate information across various topics.
The Chat Completions endpoint can generate a wide range of information, including answers to factual questions, creative writing pieces, programming help, and educational content. It supports multi-turn conversations, allowing for context-aware interactions that enhance user engagement.
Users can customize requests by adjusting parameters such as "temperature" for response randomness, "max_tokens" to limit response length, and "top_p" for nucleus sampling. These settings allow users to tailor the output to their specific needs and preferences.
The returned data is structured as a JSON object. It includes an array of "choices," each containing the assistant's message and its role. Additionally, the "usage" field provides token counts, helping users understand the complexity of their requests.
Users should check the "choices" array in the response. If it is empty, it may indicate that the model could not generate a response. Implementing error handling in the application can help manage such scenarios, prompting users to rephrase their queries if necessary.
Key fields include "id," which uniquely identifies the response; "object," indicating the type of response; "created," showing the timestamp; and "choices," which contains the assistant's generated messages. Understanding these fields helps users effectively utilize the data.
Data accuracy is maintained through ongoing training of the language model on diverse datasets. Regular updates and evaluations ensure that the model provides relevant and accurate information, enhancing the reliability of the responses generated.
Users can expect responses to follow a conversational format, with the assistant providing coherent and contextually relevant replies. The structure typically includes a clear answer or explanation, often formatted for readability, especially in creative or educational contexts.
The data covers a broad spectrum of topics, including technology, culture, science, and more. This versatility allows users to explore various categories, making it suitable for applications in education, content creation, customer support, and beyond.
Accepted parameter values include "temperature" (typically between 0 and 1), "max_tokens" (a positive integer defining the response length), and "top_p" (a float between 0 and 1 for nucleus sampling). These values help control the creativity and length of the generated responses.
The response data is structured as a JSON object containing an array of "choices." Each choice includes the assistant's message and its role (user or assistant). The "usage" field provides token counts, helping users understand their request's complexity and efficiency.
Typical use cases include developing AI chatbots for customer support, generating marketing content, providing coding assistance, and creating educational tools. Its versatility allows for applications across various industries, enhancing user engagement and productivity.
The data is derived from a wide range of sources, including books, articles, and websites, which the underlying language model has been trained on. This diverse training helps ensure that the model can provide relevant and accurate information across various topics.
Zyla API Hub is like a big store for APIs, where you can find thousands of them all in one place. We also offer dedicated support and real-time monitoring of all APIs. Once you sign up, you can pick and choose which APIs you want to use. Just remember, each API needs its own subscription. But if you subscribe to multiple ones, you'll use the same key for all of them, making things easier for you.
Prices are listed in USD (United States Dollar), EUR (Euro), CAD (Canadian Dollar), AUD (Australian Dollar), and GBP (British Pound). We accept all major debit and credit cards. Our payment system uses the latest security technology and is powered by Stripe, one of the world's most reliable payment companies. If you have any trouble paying by card, just contact us at [email protected]
Additionally, if you already have an active subscription in any of these currencies (USD, EUR, CAD, AUD, GBP), that currency will remain for subsequent subscriptions. You can change the currency at any time as long as you don't have any active subscriptions.
The local currency shown on the pricing page is based on the country of your IP address and is provided for reference only. The actual prices are in USD (United States Dollar). When you make a payment, the charge will appear on your card statement in USD, even if you see the equivalent amount in your local currency on our website. This means you cannot pay directly with your local currency.
Occasionally, a bank may decline the charge due to its fraud protection settings. We suggest reaching out to your bank initially to check if they are blocking our charges. Also, you can access the Billing Portal and change the card associated to make the payment. If these does not work and you need further assistance, please contact our team at [email protected]
Prices are determined by a recurring monthly or yearly subscription, depending on the chosen plan.
API calls are deducted from your plan based on successful requests. Each plan comes with a specific number of calls that you can make per month. Only successful calls, indicated by a Status 200 response, will be counted against your total. This ensures that failed or incomplete requests do not impact your monthly quota.
Zyla API Hub works on a recurring monthly subscription system. Your billing cycle will start the day you purchase one of the paid plans, and it will renew the same day of the next month. So be aware to cancel your subscription beforehand if you want to avoid future charges.
To upgrade your current subscription plan, simply go to the pricing page of the API and select the plan you want to upgrade to. The upgrade will be instant, allowing you to immediately enjoy the features of the new plan. Please note that any remaining calls from your previous plan will not be carried over to the new plan, so be aware of this when upgrading. You will be charged the full amount of the new plan.
To check how many API calls you have left for the current month, refer to the 'X-Zyla-API-Calls-Monthly-Remaining' field in the response header. For example, if your plan allows 1,000 requests per month and you've used 100, this field in the response header will indicate 900 remaining calls.
To see the maximum number of API requests your plan allows, check the 'X-Zyla-RateLimit-Limit' response header. For instance, if your plan includes 1,000 requests per month, this header will display 1,000.
The 'X-Zyla-RateLimit-Reset' header shows the number of seconds until your rate limit resets. This tells you when your request count will start fresh. For example, if it displays 3,600, it means 3,600 seconds are left until the limit resets.
Yes, you can cancel your plan anytime by going to your account and selecting the cancellation option on the Billing page. Please note that upgrades, downgrades, and cancellations take effect immediately. Additionally, upon cancellation, you will no longer have access to the service, even if you have remaining calls left in your quota.
You can contact us through our chat channel to receive immediate assistance. We are always online from 8 am to 5 pm (EST). If you reach us after that time, we will get back to you as soon as possible. Additionally, you can contact us via email at [email protected]
To give you the opportunity to experience our APIs without any commitment, we offer a 7-day free trial that allows you to make up to 50 API calls at no cost. This trial can be used only once, so we recommend applying it to the API that interests you the most. While most of our APIs offer a free trial, some may not. The trial concludes after 7 days or once you've made 50 requests, whichever occurs first. If you reach the 50 request limit during the trial, you will need to "Start Your Paid Plan" to continue making requests. You can find the "Start Your Paid Plan" button in your profile under Subscription -> Choose the API you are subscribed to -> Pricing tab. Alternatively, if you don't cancel your subscription before the 7th day, your free trial will end, and your plan will automatically be billed, granting you access to all the API calls specified in your plan. Please keep this in mind to avoid unwanted charges.
After 7 days, you will be charged the full amount for the plan you were subscribed to during the trial. Therefore, it's important to cancel before the trial period ends. Refund requests for forgetting to cancel on time are not accepted.
When you subscribe to an API free trial, you can make up to 50 API calls. If you wish to make additional API calls beyond this limit, the API will prompt you to perform an "Start Your Paid Plan." You can find the "Start Your Paid Plan" button in your profile under Subscription -> Choose the API you are subscribed to -> Pricing tab.
Payout Orders are processed between the 20th and the 30th of each month. If you submit your request before the 20th, your payment will be processed within this timeframe.
Service Level:
100%
Response Time:
666ms
Service Level:
100%
Response Time:
1,039ms
Service Level:
100%
Response Time:
1,931ms
Service Level:
100%
Response Time:
918ms
Service Level:
100%
Response Time:
6,950ms
Service Level:
83%
Response Time:
3,176ms
Service Level:
100%
Response Time:
744ms
Service Level:
100%
Response Time:
677ms
Service Level:
100%
Response Time:
1,645ms
Service Level:
100%
Response Time:
1,096ms
